Chroma Context-1 | A 20B Agentic Search Model
We’re introducing Chroma Context-1, a 20B parameter agentic search model that achieves retrieval performance comparable to frontier-scale LLMs at a fraction of the cost and up to 10x faster inference speed.
Join the waitlist: https://www.trychroma.com/products/agent
Full technical report: https://www.trychroma.com/research/co...
Model weights: https://huggingface.co/chromadb/conte...
Data generation codebase: https://github.com/chroma-core/contex...
0:00 - Context-1 overview
0:55 - What is agentic search?
2:13 - Context-1 agent architecture
3:47 - Evaluating performance
7:37 - Data generation
8:47 - Training Context-1
12:18 - Performance benchmarks
--
Chroma is the open-source AI application database. Batteries included.
Embeddings, vector search, document storage, full-text search, metadata filtering, and multi-modal. All in one place. Retrieval that just works. As it should be.
Try it today:
https://trychroma.com/cloud